agent-browser-cli
使用 agent-browser-cli 进行浏览器感知与控制。适用于标签页扫描/切换、页面 JS 执行、Cookie、CDP、contentSettings、截图、文件上传、下拉框点击、tmwd_cdp_bridge 初始化和 Web 工具排障
Runs with mockssource: GitHubhomepageRustMITcommit ce9a70c79ba0
Rust, MIT licensed. The project labels itself: agent, ai agent, browser automation, cdp, chrome extension, claude code, cli and codex.
agent-browser-cli runs, with stand-ins for the services it depends on. An Argusic agent installed it in 34 minutes and hit 6 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Daemon runs on default ports with config matched; with the mock extension connected, status/doctor/tabs/tabtree/scan/exec/open/close/lookup/profile-label/network/console/screenshot/save-pdf/install-skill all return ok:true and doctor reports all checks ok, while click/fill/send-keys on @e refs and mouse-click remain unverified due to mock reply-shape limits.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 92 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- standalone mock exited after ~40s due to its own read timeout9 minutes
- click/fill/send-keys on @e refs: Runtime.callFunctionOn response missing value9 minutes
- hand-rolled WebSocket mock closed right after handshake8 minutes
- scan --text-only returned empty content4 minutes
- npm global install failed with EACCES on /usr/local2 minutes
- mouse-click could not verify: element has no layout box2 minutes
- Install time
- 34 minutes
- Cold machine to finish
- 35 minutes
- Errors hit and fixed
- 6 hit, 6 fixed with no human help
- How the result was proved
- agent-browser-cli status returned healthy:true summary:ready active_tabs:1 with the mock connected; agent-browser-cli doctor returned all 8 checks ok; tabs/scan/exec/open/close/screenshot/save-pdf/network/console/lookup/profile-label each returned ok:true; node --test tests/ exited 0 (# pass 2); ffmpeg -v error -f image2 -i /tmp/verify_shot.png -f null - exited 0
- Model tokens used
- 3,570,792
- Exact commit tested
- ce9a70c79ba0
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
**Verified commands (exact)** - `npm install --prefix "$HOME/.npm-global" -g @sleepinsummer/agent-browser-cli` → `added 2 package… - `"$HOME/.npm-global/bin/agent-browser-cli" --help` → full command list, exit 0 - `agent-browser-cli status` (mock connected) → `healthy: true, summary: "ready", extension_connect… - `agent-browser-cli doctor` (mock connected) → all 8 checks true, `"ok": true` - `agent-browser-cli tabs` → `ok: true, tabs_count: 1, url: https://example.com/59` - `agent-browser-cli exec document.title` → `ok: true`, `js_return: "mock page content from fake ex… - `agent-browser-cli scan --text-only` → `ok: true, content: "mock page content from fake extension… - `node --test tests/` → `# tests 2, # pass 2, # fail 0` - `ffmpeg -v error -f image2 -i /tmp/verify_shot.png -f null -` → decoded 70-byte PNG, exit 0; `/tm… **Final state** - Daemon running on default ports (extension 18765, API 18767) with config at `~/.agent-browser-cli…
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Recovered from all 6 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Took 34 minutes to install, slower than the median of the 113 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 114 agent projects Argusic has installed and timed, agent-browser-cli was the 105th fastest to reach a running state, and 74 of 114 reached one at all.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.75 |
Topics (from GitHub)
agentai-agentbrowser-automationcdpchrome-extensionclaude-codeclicodexllm-toolsopencoderust
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/agent-browser-cli)Questions
- Does agent-browser-cli run?
- agent-browser-cli runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 34 minutes, hitting 6 errors on the way, and recorded the session.
- How did Argusic test agent-browser-cli?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit ce9a70c79ba0. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test agent-browser-cli?
- The run that produced this verdict cost $0.75: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does agent-browser-cli take to install?
- 34 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does agent-browser-cli need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing agent-browser-cli?
- 6 things broke in the recorded run, and 6 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does agent-browser-cli compare with the alternatives?
- Of the 114 agent projects Argusic has installed and timed, agent-browser-cli was the 105th fastest to reach a running state, and 74 of 114 reached one at all.
- Where is the evidence for agent-browser-cli?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.